Yanwei Pang

Jiale Cao, Yanwei Pang, Rao Muhammad Anwer et al.

We propose a novel one-step transformer-based person search framework, PSTR, that jointly performs person detection and re-identification (re-id) in a single architecture. PSTR comprises a person search-specialized (PSS) module that contains a detection encoder-decoder for person detection along with a discriminative re-id decoder for person re-id. The discriminative re-id decoder utilizes a multi-level supervision scheme with a shared decoder for discriminative re-id feature learning and also comprises a part attention block to encode relationship between different parts of a person. We further introduce a simple multi-scale scheme to support re-id across person instances at different scales. PSTR jointly achieves the diverse objectives of object-level recognition (detection) and instance-level matching (re-id). To the best of our knowledge, we are the first to propose an end-to-end one-step transformer-based person search framework. Experiments are performed on two popular benchmarks: CUHK-SYSU and PRW. Our extensive ablations reveal the merits of the proposed contributions. Further, the proposed PSTR sets a new state-of-the-art on both benchmarks. On the challenging PRW benchmark, PSTR achieves a mean average precision (mAP) score of 56.5%. The source code is available at \url{https://github.com/JialeCao001/PSTR}.

Hefeng Wang, Jiale Cao, Rao Muhammad Anwer et al.

This paper introduces an approach, named DFormer, for universal image segmentation. The proposed DFormer views universal image segmentation task as a denoising process using a diffusion model. DFormer first adds various levels of Gaussian noise to ground-truth masks, and then learns a model to predict denoising masks from corrupted masks. Specifically, we take deep pixel-level features along with the noisy masks as inputs to generate mask features and attention masks, employing diffusion-based decoder to perform mask prediction gradually. At inference, our DFormer directly predicts the masks and corresponding categories from a set of randomly-generated masks. Extensive experiments reveal the merits of our proposed contributions on different image segmentation tasks: panoptic segmentation, instance segmentation, and semantic segmentation. Our DFormer outperforms the recent diffusion-based panoptic segmentation method Pix2Seq-D with a gain of 3.6% on MS COCO val2017 set. Further, DFormer achieves promising semantic segmentation performance outperforming the recent diffusion-based method by 2.2% on ADE20K val set. Our source code and models will be publicly on https://github.com/cp3wan/DFormer

Yan Zhang, Zhong Ji, Di Wang et al.

As a fundamental and challenging task in bridging language and vision domains, Image-Text Retrieval (ITR) aims at searching for the target instances that are semantically relevant to the given query from the other modality, and its key challenge is to measure the semantic similarity across different modalities. Although significant progress has been achieved, existing approaches typically suffer from two major limitations: (1) It hurts the accuracy of the representation by directly exploiting the bottom-up attention based region-level features where each region is equally treated. (2) It limits the scale of negative sample pairs by employing the mini-batch based end-to-end training mechanism. To address these limitations, we propose a Unified Semantic Enhancement Momentum Contrastive Learning (USER) method for ITR. Specifically, we delicately design two simple but effective Global representation based Semantic Enhancement (GSE) modules. One learns the global representation via the self-attention algorithm, noted as Self-Guided Enhancement (SGE) module. The other module benefits from the pre-trained CLIP module, which provides a novel scheme to exploit and transfer the knowledge from an off-the-shelf model, noted as CLIP-Guided Enhancement (CGE) module. Moreover, we incorporate the training mechanism of MoCo into ITR, in which two dynamic queues are employed to enrich and enlarge the scale of negative sample pairs. Meanwhile, a Unified Training Objective (UTO) is developed to learn from mini-batch based and dynamic queue based samples. Extensive experiments on the benchmark MSCOCO and Flickr30K datasets demonstrate the superiority of both retrieval accuracy and inference efficiency. Our source code will be released at https://github.com/zhangy0822/USER.

Jiabei Wang, Yanwei Pang, Jiale Cao et al.

Weakly supervised person search aims to perform joint pedestrian detection and re-identification (re-id) with only person bounding-box annotations. Recently, the idea of contrastive learning is initially applied to weakly supervised person search, where two common contrast strategies are memory-based contrast and intra-image contrast. We argue that current intra-image contrast is shallow, which suffers from spatial-level and occlusion-level variance. In this paper, we present a novel deep intra-image contrastive learning using a Siamese network. Two key modules are spatial-invariant contrast (SIC) and occlusion-invariant contrast (OIC). SIC performs many-to-one contrasts between two branches of Siamese network and dense prediction contrasts in one branch of Siamese network. With these many-to-one and dense contrasts, SIC tends to learn discriminative scale-invariant and location-invariant features to solve spatial-level variance. OIC enhances feature consistency with the masking strategy to learn occlusion-invariant features. Extensive experiments are performed on two person search datasets CUHK-SYSU and PRW, respectively. Our method achieves a state-of-the-art performance among weakly supervised one-step person search approaches. We hope that our simple intra-image contrastive learning can provide more paradigms on weakly supervised person search. The source code is available at \url{https://github.com/jiabeiwangTJU/DICL}.

Zhong Ji, Zhihao Li, Yan Zhang et al.

As a promising field, Multi-Query Image Retrieval (MQIR) aims at searching for the semantically relevant image given multiple region-specific text queries. Existing works mainly focus on a single-level similarity between image regions and text queries, which neglects the hierarchical guidance of multi-level similarities and results in incomplete alignments. Besides, the high-level semantic correlations that intrinsically connect different region-query pairs are rarely considered. To address above limitations, we propose a novel Hierarchical Matching and Reasoning Network (HMRN) for MQIR. It disentangles MQIR into three hierarchical semantic representations, which is responsible to capture fine-grained local details, contextual global scopes, and high-level inherent correlations. HMRN comprises two modules: Scalar-based Matching (SM) module and Vector-based Reasoning (VR) module. Specifically, the SM module characterizes the multi-level alignment similarity, which consists of a fine-grained local-level similarity and a context-aware global-level similarity. Afterwards, the VR module is developed to excavate the potential semantic correlations among multiple region-query pairs, which further explores the high-level reasoning similarity. Finally, these three-level similarities are aggregated into a joint similarity space to form the ultimate similarity. Extensive experiments on the benchmark dataset demonstrate that our HMRN substantially surpasses the current state-of-the-art methods. For instance, compared with the existing best method Drill-down, the metric R@1 in the last round is improved by 23.4%. Our source codes will be released at https://github.com/LZH-053/HMRN.

Bin Xie, Jiale Cao, Jin Xie et al.

Open-vocabulary semantic segmentation strives to distinguish pixels into different semantic groups from an open set of categories. Most existing methods explore utilizing pre-trained vision-language models, in which the key is to adopt the image-level model for pixel-level segmentation task. In this paper, we propose a simple encoder-decoder, named SED, for open-vocabulary semantic segmentation, which comprises a hierarchical encoder-based cost map generation and a gradual fusion decoder with category early rejection. The hierarchical encoder-based cost map generation employs hierarchical backbone, instead of plain transformer, to predict pixel-level image-text cost map. Compared to plain transformer, hierarchical backbone better captures local spatial information and has linear computational complexity with respect to input size. Our gradual fusion decoder employs a top-down structure to combine cost map and the feature maps of different backbone levels for segmentation. To accelerate inference speed, we introduce a category early rejection scheme in the decoder that rejects many no-existing categories at the early layer of decoder, resulting in at most 4.7 times acceleration without accuracy degradation. Experiments are performed on multiple open-vocabulary semantic segmentation datasets, which demonstrates the efficacy of our SED method. When using ConvNeXt-B, our SED method achieves mIoU score of 31.6\% on ADE20K with 150 categories at 82 millisecond ($ms$) per image on a single A6000. We will release it at \url{https://github.com/xb534/SED.git}.

Xiaoheng Jiang, Xinyi Wu, Hisham Cholakkal et al. · ibm-research

Convolutional Neural Network (CNN) based crowd counting methods have achieved promising results in the past few years. However, the scale variation problem is still a huge challenge for accurate count estimation. In this paper, we propose a multi-scale feature aggregation network (MSFANet) that can alleviate this problem to some extent. Specifically, our approach consists of two feature aggregation modules: the short aggregation (ShortAgg) and the skip aggregation (SkipAgg). The ShortAgg module aggregates the features of the adjacent convolution blocks. Its purpose is to make features with different receptive fields fused gradually from the bottom to the top of the network. The SkipAgg module directly propagates features with small receptive fields to features with much larger receptive fields. Its purpose is to promote the fusion of features with small and large receptive fields. Especially, the SkipAgg module introduces the local self-attention features from the Swin Transformer blocks to incorporate rich spatial information. Furthermore, we present a local-and-global based counting loss by considering the non-uniform crowd distribution. Extensive experiments on four challenging datasets (ShanghaiTech dataset, UCF_CC_50 dataset, UCF-QNRF Dataset, WorldExpo'10 dataset) demonstrate the proposed easy-to-implement MSFANet can achieve promising results when compared with the previous state-of-the-art approaches.

Zhong Ji, Zhishen Hou, Xiyao Liu et al.

Few-shot Class-Incremental Learning (FSCIL) aims at learning new concepts continually with only a few samples, which is prone to suffer the catastrophic forgetting and overfitting problems. The inaccessibility of old classes and the scarcity of the novel samples make it formidable to realize the trade-off between retaining old knowledge and learning novel concepts. Inspired by that different models memorize different knowledge when learning novel concepts, we propose a Memorizing Complementation Network (MCNet) to ensemble multiple models that complements the different memorized knowledge with each other in novel tasks. Additionally, to update the model with few novel samples, we develop a Prototype Smoothing Hard-mining Triplet (PSHT) loss to push the novel samples away from not only each other in current task but also the old distribution. Extensive experiments on three benchmark datasets, e.g., CIFAR100, miniImageNet and CUB200, have demonstrated the superiority of our proposed method.

Xiaohan Liu, Yanwei Pang, Ruiqi Jin et al.

Purpose: To introduce a dual-domain reconstruction network with V-Net and K-Net for accurate MR image reconstruction from undersampled k-space data. Methods: Most state-of-the-art reconstruction methods apply U-Net or cascaded U-Nets in image domain and/or k-space domain. Nevertheless, these methods have following problems: (1) Directly applying U-Net in k-space domain is not optimal for extracting features in k-space domain; (2) Classical image-domain oriented U-Net is heavy-weight and hence is inefficient to be cascaded many times for yielding good reconstruction accuracy; (3) Classical image-domain oriented U-Net does not fully make use information of encoder network for extracting features in decoder network; and (4) Existing methods are ineffective in simultaneously extracting and fusing features in image domain and its dual k-space domain. To tackle these problems, we propose in this paper (1) an image-domain encoder-decoder sub-network called V-Net which is more light-weight for cascading and effective in fully utilizing features in the encoder for decoding, (2) a k-space domain sub-network called K-Net which is more suitable for extracting hierarchical features in k-space domain, and (3) a dual-domain reconstruction network where V-Nets and K-Nets are parallelly and effectively combined and cascaded. Results: Extensive experimental results on the challenging fastMRI dataset demonstrate that the proposed KV-Net can reconstruct high-quality images and outperform current state-of-the-art approaches with fewer parameters. Conclusions: To reconstruct images effectively and efficiently from incomplete k-space data, we have presented a parallel dual-domain KV-Net to combine K-Nets and V-Nets. The KV-Net is more lightweight than state-of-the-art methods but achieves better reconstruction performance.

Zhong Ji, Liyuan Hou, Xuan Wang et al.

Few-shot remote sensing image scene classification (FS-RSISC) aims at classifying remote sensing images with only a few labeled samples. The main challenges lie in small inter-class variances and large intra-class variances, which are the inherent property of remote sensing images. To address these challenges, we propose a transfer-based Dual Contrastive Network (DCN), which incorporates two auxiliary supervised contrastive learning branches during the training process. Specifically, one is a Context-guided Contrastive Learning (CCL) branch and the other is a Detail-guided Contrastive Learning (DCL) branch, which focus on inter-class discriminability and intra-class invariance, respectively. In the CCL branch, we first devise a Condenser Network to capture context features, and then leverage a supervised contrastive learning on top of the obtained context features to facilitate the model to learn more discriminative features. In the DCL branch, a Smelter Network is designed to highlight the significant local detail information. And then we construct a supervised contrastive learning based on the detail feature maps to fully exploit the spatial information in each map, enabling the model to concentrate on invariant detail features. Extensive experiments on four public benchmark remote sensing datasets demonstrate the competitive performance of our proposed DCN.

Hanqing Sun, Yanwei Pang, Jiale Cao et al.

Transformers have shown promising progress in various visual object detection tasks, including monocular 2D/3D detection and surround-view 3D detection. More importantly, the attention mechanism in the Transformer model and the 3D information extraction in binocular stereo are both similarity-based. However, directly applying existing Transformer-based detectors to binocular stereo 3D object detection leads to slow convergence and significant precision drops. We argue that a key cause of that defect is that existing Transformers ignore the binocular-stereo-specific image correspondence information. In this paper, we explore the model design of Transformers in binocular 3D object detection, focusing particularly on extracting and encoding task-specific image correspondence information. To achieve this goal, we present TS3D, a Transformer-based Stereo-aware 3D object detector. In the TS3D, a Disparity-Aware Positional Encoding (DAPE) module is proposed to embed the image correspondence information into stereo features. The correspondence is encoded as normalized sub-pixel-level disparity and is used in conjunction with sinusoidal 2D positional encoding to provide the 3D location information of the scene. To enrich multi-scale stereo features, we propose a Stereo Preserving Feature Pyramid Network (SPFPN). The SPFPN is designed to preserve the correspondence information while fusing intra-scale and aggregating cross-scale stereo features. Our proposed TS3D achieves a 41.29% Moderate Car detection average precision on the KITTI test set and takes 88 ms to detect objects from each binocular image pair. It is competitive with advanced counterparts in terms of both precision and inference speed.

Xiaohan Liu, Yanwei Pang, Xuebin Sun et al.

Partial scan is a common approach to accelerate Magnetic Resonance Imaging (MRI) data acquisition in both 2D and 3D settings. However, accurately reconstructing images from partial scan data (i.e., incomplete k-space matrices) remains challenging due to lack of an effectively global receptive field in both spatial and k-space domains. To address this problem, we propose the following: (1) a novel convolutional operator called Faster Fourier Convolution (FasterFC) to replace the two consecutive convolution operations typically used in convolutional neural networks (e.g., U-Net, ResNet). Based on the spectral convolution theorem in Fourier theory, FasterFC employs alternating kernels of size 1 in 3D case) in different domains to extend the dual-domain receptive field to the global and achieves faster calculation speed than traditional Fast Fourier Convolution (FFC). (2) A 2D accelerated MRI method, FasterFC-End-to-End-VarNet, which uses FasterFC to improve the sensitivity maps and reconstruction quality. (3) A multi-stage 3D accelerated MRI method called FasterFC-based Single-to-group Network (FAS-Net) that utilizes a single-to-group algorithm to guide k-space domain reconstruction, followed by FasterFC-based cascaded convolutional neural networks to expand the effective receptive field in the dual-domain. Experimental results on the fastMRI and Stanford MRI Data datasets demonstrate that FasterFC improves the quality of both 2D and 3D reconstruction. Moreover, FAS-Net, as a 3D high-resolution multi-coil (eight) accelerated MRI method, achieves superior reconstruction performance in both qualitative and quantitative results compared with state-of-the-art 2D and 3D methods.

Yiming Liu, Yanwei Pang, Ruiqi Jin et al.

Purpose: Long scan time in phase encoding for forming complete K-space matrices is a critical drawback of MRI, making patients uncomfortable and wasting important time for diagnosing emergent diseases. This paper aims to reducing the scan time by actively and sequentially selecting partial phases in a short time so that a slice can be accurately reconstructed from the resultant slice-specific incomplete K-space matrix. Methods: A transformer based deep reinforcement learning framework is proposed for actively determining a sequence of partial phases according to reconstruction-quality based Q-value (a function of reward), where the reward is the improvement degree of reconstructed image quality. The Q-value is efficiently predicted from binary phase-indicator vectors, incomplete K-space matrices and their corresponding undersampled images with a light-weight transformer so that the sequential information of phases and global relationship in images can be used. The inverse Fourier transform is employed for efficiently computing the undersampled images and hence gaining the rewards of selecting phases. Results: Experimental results on the fastMRI dataset with original K-space data accessible demonstrate the efficiency and accuracy superiorities of proposed method. Compared with the state-of-the-art reinforcement learning based method proposed by Pineda et al., the proposed method is roughly 150 times faster and achieves significant improvement in reconstruction accuracy. Conclusions: We have proposed a light-weight transformer based deep reinforcement learning framework for generating high-quality slice-specific trajectory consisting of a small number of phases. The proposed method, called TITLE (Transformer Involved Trajectory LEarning), has remarkable superiority in phase-encode selection efficiency and image reconstruction accuracy.

Zhiqiang Dong, Jiale Cao, Rao Muhammad Anwer et al.

We propose an end-to-end one-step person search approach with learnable proposals, named LEAPS. Given a set of sparse and learnable proposals, LEAPS employs a dynamic person search head to directly perform person detection and corresponding re-id feature generation without non-maximum suppression post-processing. The dynamic person search head comprises a detection head and a novel flexible re-id head. Our flexible re-id head first employs a dynamic region-of-interest (RoI) operation to extract discriminative RoI features of the proposals. Then, it generates re-id features using a plain and a hierarchical interaction re-id module. To better guide discriminative re-id feature learning, we introduce a diverse re-id sample matching strategy, instead of bipartite matching in detection head. Comprehensive experiments reveal the benefit of the proposed LEAPS, achieving a favorable performance on two public person search benchmarks: CUHK-SYSU and PRW. When using the same ResNet50 backbone, our LEAPS obtains a mAP score of 55.0%, outperforming the best reported results in literature by 1.7%, while achieving around a two-fold speedup on the challenging PRW dataset. Our source code and models will be released.

Lin Sun, Jiale Cao, Jin Xie et al.

Stable diffusion has demonstrated strong image synthesis ability to given text descriptions, suggesting it to contain strong semantic clue for grouping objects. The researchers have explored employing stable diffusion for training-free segmentation. Most existing approaches refine cross-attention map by self-attention map once, demonstrating that self-attention map contains useful semantic information to improve segmentation. To fully utilize self-attention map, we present a deep experimental analysis on iteratively refining cross-attention map with self-attention map, and propose an effective iterative refinement framework for training-free segmentation, named iSeg. The proposed iSeg introduces an entropy-reduced self-attention module that utilizes a gradient descent scheme to reduce the entropy of self-attention map, thereby suppressing the weak responses corresponding to irrelevant global information. Leveraging the entropy-reduced self-attention module, our iSeg stably improves refined cross-attention map with iterative refinement. Further, we design a category-enhanced cross-attention module to generate accurate cross-attention map, providing a better initial input for iterative refinement. Extensive experiments across different datasets and diverse segmentation tasks reveal the merits of proposed contributions, leading to promising performance on diverse segmentation tasks. For unsupervised semantic segmentation on Cityscapes, our iSeg achieves an absolute gain of 3.8% in terms of mIoU compared to the best existing training-free approach in literature. Moreover, our proposed iSeg can support segmentation with different kinds of images and interactions. The project is available at https://linsun449.github.io/iSeg.

Yuzhe Chen, Jiale Cao, Xuyang Liu et al.

Diffusion Large Language Models (dLLMs) have achieved rapid progress, viewed as a promising alternative to the autoregressive paradigm. However, most dLLM decoders still adopt a global confidence threshold, and do not explicitly model local context from neighboring decoded states or temporal consistency of predicted token IDs across steps. To address this issue, we propose a simple spatio-temporal stability guided decoding approach, named STDec. We observe strong spatio-temporal stability in dLLM decoding: newly decoded tokens tend to lie near decoded neighbors, and their predicted IDs often remain consistent across several denoising steps. Inspired by this stability, our STDec includes spatial-aware decoding and temporal-aware decoding. The spatial-aware decoding dynamically generates the token-adaptive threshold by aggregating the decoded states of nearby tokens. The temporal-aware decoding relaxes the decoding thresholds for tokens whose predicted token IDs remain consistent over denoising steps. Our STDec is training-free and remains compatible with cache-based acceleration methods. Across textual reasoning and multimodal understanding benchmarks, STDec substantially improves throughput while maintaining comparable task performance score. Notably, on MBPP with LLaDA, STDec achieves up to 14.17x speedup with a comparable score. Homepage: https://yzchen02.github.io/STDec.

Jingren Liu, Zhong Ji, YunLong Yu et al.

Parameter-efficient fine-tuning for continual learning (PEFT-CL) has shown promise in adapting pre-trained models to sequential tasks while mitigating catastrophic forgetting problem. However, understanding the mechanisms that dictate continual performance in this paradigm remains elusive. To unravel this mystery, we undertake a rigorous analysis of PEFT-CL dynamics to derive relevant metrics for continual scenarios using Neural Tangent Kernel (NTK) theory. With the aid of NTK as a mathematical analysis tool, we recast the challenge of test-time forgetting into the quantifiable generalization gaps during training, identifying three key factors that influence these gaps and the performance of PEFT-CL: training sample size, task-level feature orthogonality, and regularization. To address these challenges, we introduce NTK-CL, a novel framework that eliminates task-specific parameter storage while adaptively generating task-relevant features. Aligning with theoretical guidance, NTK-CL triples the feature representation of each sample, theoretically and empirically reducing the magnitude of both task-interplay and task-specific generalization gaps. Grounded in NTK analysis, our framework imposes an adaptive exponential moving average mechanism and constraints on task-level feature orthogonality, maintaining intra-task NTK forms while attenuating inter-task NTK forms. Ultimately, by fine-tuning optimizable parameters with appropriate regularization, NTK-CL achieves state-of-the-art performance on established PEFT-CL benchmarks. This work provides a theoretical foundation for understanding and improving PEFT-CL models, offering insights into the interplay between feature representation, task orthogonality, and generalization, contributing to the development of more efficient continual learning systems.

Yan Zhang, Zhong Ji, Changxu Meng et al.

Recent studies focus on the Remote Sensing Image-Text Retrieval (RSITR), which aims at searching for the corresponding targets based on the given query. Among these efforts, the application of Foundation Models (FMs), such as CLIP, to the domain of remote sensing has yielded encouraging outcomes. However, existing FM based methodologies neglect the negative impact of weakly correlated sample pairs and fail to account for the key distinctions among remote sensing texts, leading to biased and superficial exploration of sample pairs. To address these challenges, we propose an approach named iEBAKER (an Improved Eliminate Before Align strategy with Keyword Explicit Reasoning framework) for RSITR. Specifically, we propose an innovative Eliminate Before Align (EBA) strategy to filter out the weakly correlated sample pairs, thereby mitigating their deviations from optimal embedding space during alignment.Further, two specific schemes are introduced from the perspective of whether local similarity and global similarity affect each other. On this basis, we introduce an alternative Sort After Reversed Retrieval (SAR) strategy, aims at optimizing the similarity matrix via reverse retrieval. Additionally, we incorporate a Keyword Explicit Reasoning (KER) module to facilitate the beneficial impact of subtle key concept distinctions. Without bells and whistles, our approach enables a direct transition from FM to RSITR task, eliminating the need for additional pretraining on remote sensing data. Extensive experiments conducted on three popular benchmark datasets demonstrate that our proposed iEBAKER method surpasses the state-of-the-art models while requiring less training data. Our source code will be released at https://github.com/zhangy0822/iEBAKER.

Wenqi Zhu, Jiale Cao, Jin Xie et al.

Open-vocabulary video instance segmentation strives to segment and track instances belonging to an open set of categories in a videos. The vision-language model Contrastive Language-Image Pre-training (CLIP) has shown robust zero-shot classification ability in image-level open-vocabulary tasks. In this paper, we propose a simple encoder-decoder network, called CLIP-VIS, to adapt CLIP for open-vocabulary video instance segmentation. Our CLIP-VIS adopts frozen CLIP and introduces three modules, including class-agnostic mask generation, temporal topK-enhanced matching, and weighted open-vocabulary classification. Given a set of initial queries, class-agnostic mask generation introduces a pixel decoder and a transformer decoder on CLIP pre-trained image encoder to predict query masks and corresponding object scores and mask IoU scores. Then, temporal topK-enhanced matching performs query matching across frames using the K mostly matched frames. Finally, weighted open-vocabulary classification first employs mask pooling to generate query visual features from CLIP pre-trained image encoder, and second performs weighted classification using object scores and mask IoU scores. Our CLIP-VIS does not require the annotations of instance categories and identities. The experiments are performed on various video instance segmentation datasets, which demonstrate the effectiveness of our proposed method, especially for novel categories. When using ConvNeXt-B as backbone, our CLIP-VIS achieves the AP and APn scores of 32.2% and 40.2% on the validation set of LV-VIS dataset, which outperforms OV2Seg by 11.1% and 23.9% respectively. We will release the source code and models at https://github.com/zwq456/CLIP-VIS.git.

Yanwei Pang, Jiale Cao, Yazhao Li et al.

Vehicles, pedestrians, and riders are the most important and interesting objects for the perception modules of self-driving vehicles and video surveillance. However, the state-of-the-art performance of detecting such important objects (esp. small objects) is far from satisfying the demand of practical systems. Large-scale, rich-diversity, and high-resolution datasets play an important role in developing better object detection methods to satisfy the demand. Existing public large-scale datasets such as MS COCO collected from websites do not focus on the specific scenarios. Moreover, the popular datasets (e.g., KITTI and Citypersons) collected from the specific scenarios are limited in the number of images and instances, the resolution, and the diversity. To attempt to solve the problem, we build a diverse high-resolution dataset (called TJU-DHD). The dataset contains 115,354 high-resolution images (52% images have a resolution of 1624$\times$1200 pixels and 48% images have a resolution of at least 2,560$\times$1,440 pixels) and 709,330 labeled objects in total with a large variance in scale and appearance. Meanwhile, the dataset has a rich diversity in season variance, illumination variance, and weather variance. In addition, a new diverse pedestrian dataset is further built. With the four different detectors (i.e., the one-stage RetinaNet, anchor-free FCOS, two-stage FPN, and Cascade R-CNN), experiments about object detection and pedestrian detection are conducted. We hope that the newly built dataset can help promote the research on object detection and pedestrian detection in these two scenes. The dataset is available at https://github.com/tjubiit/TJU-DHD.

Jiale Cao, Yanwei Pang, Jin Xie et al.

Pedestrian detection is an important but challenging problem in computer vision, especially in human-centric tasks. Over the past decade, significant improvement has been witnessed with the help of handcrafted features and deep features. Here we present a comprehensive survey on recent advances in pedestrian detection. First, we provide a detailed review of single-spectral pedestrian detection that includes handcrafted features based methods and deep features based approaches. For handcrafted features based methods, we present an extensive review of approaches and find that handcrafted features with large freedom degrees in shape and space have better performance. In the case of deep features based approaches, we split them into pure CNN based methods and those employing both handcrafted and CNN based features. We give the statistical analysis and tendency of these methods, where feature enhanced, part-aware, and post-processing methods have attracted main attention. In addition to single-spectral pedestrian detection, we also review multi-spectral pedestrian detection, which provides more robust features for illumination variance. Furthermore, we introduce some related datasets and evaluation metrics, and compare some representative methods. We conclude this survey by emphasizing open problems that need to be addressed and highlighting various future directions. Researchers can track an up-to-date list at https://github.com/JialeCao001/PedSurvey.

Jiale Cao, Rao Muhammad Anwer, Hisham Cholakkal et al.

Single-stage instance segmentation approaches have recently gained popularity due to their speed and simplicity, but are still lagging behind in accuracy, compared to two-stage methods. We propose a fast single-stage instance segmentation method, called SipMask, that preserves instance-specific spatial information by separating mask prediction of an instance to different sub-regions of a detected bounding-box. Our main contribution is a novel light-weight spatial preservation (SP) module that generates a separate set of spatial coefficients for each sub-region within a bounding-box, leading to improved mask predictions. It also enables accurate delineation of spatially adjacent instances. Further, we introduce a mask alignment weighting loss and a feature alignment scheme to better correlate mask prediction with object detection. On COCO test-dev, our SipMask outperforms the existing single-stage methods. Compared to the state-of-the-art single-stage TensorMask, SipMask obtains an absolute gain of 1.0% (mask AP), while providing a four-fold speedup. In terms of real-time capabilities, SipMask outperforms YOLACT with an absolute gain of 3.0% (mask AP) under similar settings, while operating at comparable speed on a Titan Xp. We also evaluate our SipMask for real-time video instance segmentation, achieving promising results on YouTube-VIS dataset. The source code is available at https://github.com/JialeCao001/SipMask.

Haoran Wang, Ying Zhang, Zhong Ji et al.

Image-text matching plays a central role in bridging vision and language. Most existing approaches only rely on the image-text instance pair to learn their representations, thereby exploiting their matching relationships and making the corresponding alignments. Such approaches only exploit the superficial associations contained in the instance pairwise data, with no consideration of any external commonsense knowledge, which may hinder their capabilities to reason the higher-level relationships between image and text. In this paper, we propose a Consensus-aware Visual-Semantic Embedding (CVSE) model to incorporate the consensus information, namely the commonsense knowledge shared between both modalities, into image-text matching. Specifically, the consensus information is exploited by computing the statistical co-occurrence correlations between the semantic concepts from the image captioning corpus and deploying the constructed concept correlation graph to yield the consensus-aware concept (CAC) representations. Afterwards, CVSE learns the associations and alignments between image and text based on the exploited consensus as well as the instance-level representations for both modalities. Extensive experiments conducted on two public datasets verify that the exploited consensus makes significant contributions to constructing more meaningful visual-semantic embeddings, with the superior performances over the state-of-the-art approaches on the bidirectional image and text retrieval task. Our code of this paper is available at: https://github.com/BruceW91/CVSE.

Yanwei Pang, Jin Xie, Muhammad Haris Khan et al.

Pedestrian detection relying on deep convolution neural networks has made significant progress. Though promising results have been achieved on standard pedestrians, the performance on heavily occluded pedestrians remains far from satisfactory. The main culprits are intra-class occlusions involving other pedestrians and inter-class occlusions caused by other objects, such as cars and bicycles. These result in a multitude of occlusion patterns. We propose an approach for occluded pedestrian detection with the following contributions. First, we introduce a novel mask-guided attention network that fits naturally into popular pedestrian detection pipelines. Our attention network emphasizes on visible pedestrian regions while suppressing the occluded ones by modulating full body features. Second, we empirically demonstrate that coarse-level segmentation annotations provide reasonable approximation to their dense pixel-wise counterparts. Experiments are performed on CityPersons and Caltech datasets. Our approach sets a new state-of-the-art on both datasets. Our approach obtains an absolute gain of 9.5% in log-average miss rate, compared to the best reported results on the heavily occluded (HO) pedestrian set of CityPersons test set. Further, on the HO pedestrian set of Caltech dataset, our method achieves an absolute gain of 5.0% in log-average miss rate, compared to the best reported results. Code and models are available at: https://github.com/Leotju/MGAN.

Zhijie Zhang, Huazhu Fu, Hang Dai et al.

Segmentation is a fundamental task in medical image analysis. However, most existing methods focus on primary region extraction and ignore edge information, which is useful for obtaining accurate segmentation. In this paper, we propose a generic medical segmentation method, called Edge-aTtention guidance Network (ET-Net), which embeds edge-attention representations to guide the segmentation network. Specifically, an edge guidance module is utilized to learn the edge-attention representations in the early encoding layers, which are then transferred to the multi-scale decoding layers, fused using a weighted aggregation module. The experimental results on four segmentation tasks (i.e., optic disc/cup and vessel segmentation in retinal images, and lung segmentation in chest X-Ray and CT images) demonstrate that preserving edge-attention representations contributes to the final segmentation accuracy, and our proposed method outperforms current state-of-the-art segmentation methods. The source code of our method is available at https://github.com/ZzzJzzZ/ETNet.

Xiaoheng Jiang, Feng Yan, Yang Lu et al.

Surface defect inspection plays an important role in the process of industrial manufacture and production. Though Convolutional Neural Network (CNN) based defect inspection methods have made huge leaps, they still confront a lot of challenges such as defect scale variation, complex background, low contrast, and so on. To address these issues, we propose a joint attention-guided feature fusion network (JAFFNet) for saliency detection of surface defects based on the encoder-decoder network. JAFFNet mainly incorporates a joint attention-guided feature fusion (JAFF) module into decoding stages to adaptively fuse low-level and high-level features. The JAFF module learns to emphasize defect features and suppress background noise during feature fusion, which is beneficial for detecting low-contrast defects. In addition, JAFFNet introduces a dense receptive field (DRF) module following the encoder to capture features with rich context information, which helps detect defects of different scales. The JAFF module mainly utilizes a learned joint channel-spatial attention map provided by high-level semantic features to guide feature fusion. The attention map makes the model pay more attention to defect features. The DRF module utilizes a sequence of multi-receptive-field (MRF) units with each taking as inputs all the preceding MRF feature maps and the original input. The obtained DRF features capture rich context information with a large range of receptive fields. Extensive experiments conducted on SD-saliency-900, Magnetic tile, and DAGM 2007 indicate that our method achieves promising performance in comparison with other state-of-the-art methods. Meanwhile, our method reaches a real-time defect detection speed of 66 FPS.

Lin Sun, Jiale Cao, Jin Xie et al.

Contrastive Language-Image Pre-training (CLIP) exhibits strong zero-shot classification ability on various image-level tasks, leading to the research to adapt CLIP for pixel-level open-vocabulary semantic segmentation without additional training. The key is to improve spatial representation of image-level CLIP, such as replacing self-attention map at last layer with self-self attention map or vision foundation model based attention map. In this paper, we present a novel hierarchical framework, named CLIPer, that hierarchically improves spatial representation of CLIP. The proposed CLIPer includes an early-layer fusion module and a fine-grained compensation module. We observe that, the embeddings and attention maps at early layers can preserve spatial structural information. Inspired by this, we design the early-layer fusion module to generate segmentation map with better spatial coherence. Afterwards, we employ a fine-grained compensation module to compensate the local details using the self-attention maps of diffusion model. We conduct the experiments on seven segmentation datasets. Our proposed CLIPer achieves the state-of-the-art performance on these datasets. For instance, using ViT-L, CLIPer has the mIoU of 69.8% and 43.3% on VOC and COCO Object, outperforming ProxyCLIP by 9.2% and 4.1% respectively.

Zhong Ji, Yimu Su, Yan Zhang et al.

Video Wire Inpainting (VWI) is a prominent application in video inpainting, aimed at flawlessly removing wires in films or TV series, offering significant time and labor savings compared to manual frame-by-frame removal. However, wire removal poses greater challenges due to the wires being longer and slimmer than objects typically targeted in general video inpainting tasks, and often intersecting with people and background objects irregularly, which adds complexity to the inpainting process. Recognizing the limitations posed by existing video wire datasets, which are characterized by their small size, poor quality, and limited variety of scenes, we introduce a new VWI dataset with a novel mask generation strategy, namely Wire Removal Video Dataset 2 (WRV2) and Pseudo Wire-Shaped (PWS) Masks. WRV2 dataset comprises over 4,000 videos with an average length of 80 frames, designed to facilitate the development and efficacy of inpainting models. Building upon this, our research proposes the Redundancy-Aware Transformer (Raformer) method that addresses the unique challenges of wire removal in video inpainting. Unlike conventional approaches that indiscriminately process all frame patches, Raformer employs a novel strategy to selectively bypass redundant parts, such as static background segments devoid of valuable information for inpainting. At the core of Raformer is the Redundancy-Aware Attention (RAA) module, which isolates and accentuates essential content through a coarse-grained, window-based attention mechanism. This is complemented by a Soft Feature Alignment (SFA) module, which refines these features and achieves end-to-end feature alignment. Extensive experiments on both the traditional video inpainting datasets and our proposed WRV2 dataset demonstrate that Raformer outperforms other state-of-the-art methods.

Bonan Ding, Jin Xie, Jing Nie et al.

Due to its cost-effectiveness and widespread availability, monocular 3D object detection, which relies solely on a single camera during inference, holds significant importance across various applications, including autonomous driving and robotics. Nevertheless, directly predicting the coordinates of objects in 3D space from monocular images poses challenges. Therefore, an effective solution involves transforming monocular images into LiDAR-like representations and employing a LiDAR-based 3D object detector to predict the 3D coordinates of objects. The key step in this method is accurately converting the monocular image into a reliable point cloud form. In this paper, we present VFMM3D, an innovative framework that leverages the capabilities of Vision Foundation Models (VFMs) to accurately transform single-view images into LiDAR point cloud representations. VFMM3D utilizes the Segment Anything Model (SAM) and Depth Anything Model (DAM) to generate high-quality pseudo-LiDAR data enriched with rich foreground information. Specifically, the Depth Anything Model (DAM) is employed to generate dense depth maps. Subsequently, the Segment Anything Model (SAM) is utilized to differentiate foreground and background regions by predicting instance masks. These predicted instance masks and depth maps are then combined and projected into 3D space to generate pseudo-LiDAR points. Finally, any object detectors based on point clouds can be utilized to predict the 3D coordinates of objects. Comprehensive experiments are conducted on two challenging 3D object detection datasets, KITTI and Waymo. Our VFMM3D establishes a new state-of-the-art performance on both datasets. Additionally, experimental results demonstrate the generality of VFMM3D, showcasing its seamless integration into various LiDAR-based 3D object detectors.

Hongsheng Zhang, Zhong Ji, Jingren Liu et al.

Vision Language Models (VLMs), pre-trained on large-scale image-text datasets, enable zero-shot predictions for unseen data but may underperform on specific unseen tasks. Continual learning (CL) can help VLMs effectively adapt to new data distributions without joint training, but faces challenges of catastrophic forgetting and generalization forgetting. Although significant progress has been achieved by distillation-based methods, they exhibit two severe limitations. One is the popularly adopted single-teacher paradigm fails to impart comprehensive knowledge, The other is the existing methods inadequately leverage the multimodal information in the original training dataset, instead they rely on additional data for distillation, which increases computational and storage overhead. To mitigate both limitations, by drawing on Knowledge Integration Theory (KIT), we propose a Multi-Stage Knowledge Integration network (MulKI) to emulate the human learning process in distillation methods. MulKI achieves this through four stages, including Eliciting Ideas, Adding New Ideas, Distinguishing Ideas, and Making Connections. During the four stages, we first leverage prototypes to align across modalities, eliciting cross-modal knowledge, then adding new knowledge by constructing fine-grained intra- and inter-modality relationships with prototypes. After that, knowledge from two teacher models is adaptively distinguished and re-weighted. Finally, we connect between models from intra- and inter-task, integrating preceding and new knowledge. Our method demonstrates significant improvements in maintaining zero-shot capabilities while supporting continual learning across diverse downstream tasks, showcasing its potential in adapting VLMs to evolving data distributions.

Zhong Ji, Shuo Yang, Jingren Liu et al.

Generalized Category Discovery (GCD) aims to classify both base and novel images using labeled base data. However, current approaches inadequately address the intrinsic optimization of the co-occurrence matrix $\bar{A}$ based on cosine similarity, failing to achieve zero base-novel regions and adequate sparsity in base and novel domains. To address these deficiencies, we propose a Non-Negative Generalized Category Discovery (NN-GCD) framework. It employs Symmetric Non-negative Matrix Factorization (SNMF) as a mathematical medium to prove the equivalence of optimal K-means with optimal SNMF, and the equivalence of SNMF solver with non-negative contrastive learning (NCL) optimization. Utilizing these theoretical equivalences, it reframes the optimization of $\bar{A}$ and K-means clustering as an NCL optimization problem. Moreover, to satisfy the non-negative constraints and make a GCD model converge to a near-optimal region, we propose a GELU activation function and an NMF NCE loss. To transition $\bar{A}$ from a suboptimal state to the desired $\bar{A}^*$, we introduce a hybrid sparse regularization approach to impose sparsity constraints. Experimental results show NN-GCD outperforms state-of-the-art methods on GCD benchmarks, achieving an average accuracy of 66.1\% on the Semantic Shift Benchmark, surpassing prior counterparts by 4.7\%.

Hefeng Wang, Jiale Cao, Jin Xie et al.

Text-to-image diffusion models have shown powerful ability on conditional image synthesis. With large-scale vision-language pre-training, diffusion models are able to generate high-quality images with rich texture and reasonable structure under different text prompts. However, it is an open problem to adapt the pre-trained diffusion model for visual perception. In this paper, we propose an implicit and explicit language guidance framework for diffusion-based perception, named IEDP. Our IEDP comprises an implicit language guidance branch and an explicit language guidance branch. The implicit branch employs frozen CLIP image encoder to directly generate implicit text embeddings that are fed to diffusion model, without using explicit text prompts. The explicit branch utilizes the ground-truth labels of corresponding images as text prompts to condition feature extraction of diffusion model. During training, we jointly train diffusion model by sharing the model weights of these two branches. As a result, implicit and explicit branches can jointly guide feature learning. During inference, we only employ implicit branch for final prediction, which does not require any ground-truth labels. Experiments are performed on two typical perception tasks, including semantic segmentation and depth estimation. Our IEDP achieves promising performance on both tasks. For semantic segmentation, our IEDP has the mIoU$^\text{ss}$ score of 55.9% on AD20K validation set, which outperforms the baseline method VPD by 2.2%. For depth estimation, our IEDP outperforms the baseline method VPD with a relative gain of 11.0%.

Ronghua Xu, Jin Xie, Jing Nie et al.

Spiking Neural Networks (SNNs), characterized by discrete binary activations, offer high computational efficiency and low energy consumption, making them well-suited for computation-intensive tasks such as stereo image restoration. In this work, we propose SNNSIR, a simple yet effective Spiking Neural Network for Stereo Image Restoration, specifically designed under the spike-driven paradigm where neurons transmit information through sparse, event-based binary spikes. In contrast to existing hybrid SNN-ANN models that still rely on operations such as floating-point matrix division or exponentiation, which are incompatible with the binary and event-driven nature of SNNs, our proposed SNNSIR adopts a fully spike-driven architecture to achieve low-power and hardware-friendly computation. To address the expressiveness limitations of binary spiking neurons, we first introduce a lightweight Spike Residual Basic Block (SRBB) to enhance information flow via spike-compatible residual learning. Building on this, the Spike Stereo Convolutional Modulation (SSCM) module introduces simplified nonlinearity through element-wise multiplication and highlights noise-sensitive regions via cross-view-aware modulation. Complementing this, the Spike Stereo Cross-Attention (SSCA) module further improves stereo correspondence by enabling efficient bidirectional feature interaction across views within a spike-compatible framework. Extensive experiments on diverse stereo image restoration tasks, including rain streak removal, raindrop removal, low-light enhancement, and super-resolution demonstrate that our model achieves competitive restoration performance while significantly reducing computational overhead. These results highlight the potential for real-time, low-power stereo vision applications. The code will be available after the article is accepted.

Zhong Ji, Rongshuai Wei, Jingren Liu et al.

Self-Explainable Models (SEMs) rely on Prototypical Concept Learning (PCL) to enable their visual recognition processes more interpretable, but they often struggle in data-scarce settings where insufficient training samples lead to suboptimal performance.To address this limitation, we propose a Few-Shot Prototypical Concept Classification (FSPCC) framework that systematically mitigates two key challenges under low-data regimes: parametric imbalance and representation misalignment. Specifically, our approach leverages a Mixture of LoRA Experts (MoLE) for parameter-efficient adaptation, ensuring a balanced allocation of trainable parameters between the backbone and the PCL module.Meanwhile, cross-module concept guidance enforces tight alignment between the backbone's feature representations and the prototypical concept activation patterns.In addition, we incorporate a multi-level feature preservation strategy that fuses spatial and semantic cues across various layers, thereby enriching the learned representations and mitigating the challenges posed by limited data availability.Finally, to enhance interpretability and minimize concept overlap, we introduce a geometry-aware concept discrimination loss that enforces orthogonality among concepts, encouraging more disentangled and transparent decision boundaries.Experimental results on six popular benchmarks (CUB-200-2011, mini-ImageNet, CIFAR-FS, Stanford Cars, FGVC-Aircraft, and DTD) demonstrate that our approach consistently outperforms existing SEMs by a notable margin, with 4.2%-8.7% relative gains in 5-way 5-shot classification.These findings highlight the efficacy of coupling concept learning with few-shot adaptation to achieve both higher accuracy and clearer model interpretability, paving the way for more transparent visual recognition systems.

Yanbei Liu, Chongxu Wang, Zhitao Xiao et al.

Heterogeneous Graph Neural Networks (HGNNs), have demonstrated excellent capabilities in processing heterogeneous information networks. Self-supervised learning on heterogeneous graphs, especially contrastive self-supervised strategy, shows great potential when there are no labels. However, this approach requires the use of carefully designed graph augmentation strategies and the selection of positive and negative samples. Determining the exact level of similarity between sample pairs is non-trivial.To solve this problem, we propose a novel self-supervised Heterogeneous graph neural network with Optimal Transport (HGOT) method which is designed to facilitate self-supervised learning for heterogeneous graphs without graph augmentation strategies. Different from traditional contrastive self-supervised learning, HGOT employs the optimal transport mechanism to relieve the laborious sampling process of positive and negative samples. Specifically, we design an aggregating view (central view) to integrate the semantic information contained in the views represented by different meta-paths (branch views). Then, we introduce an optimal transport plan to identify the transport relationship between the semantics contained in the branch view and the central view. This allows the optimal transport plan between graphs to align with the representations, forcing the encoder to learn node representations that are more similar to the graph space and of higher quality. Extensive experiments on four real-world datasets demonstrate that our proposed HGOT model can achieve state-of-the-art performance on various downstream tasks. In particular, in the node classification task, HGOT achieves an average of more than 6% improvement in accuracy compared with state-of-the-art methods.

Zhong Ji, Ci Liu, Jingren Liu et al.

Few-Shot Remote Sensing Scene Classification (FS-RSSC) presents the challenge of classifying remote sensing images with limited labeled samples. Existing methods typically emphasize single-modal feature learning, neglecting the potential benefits of optimizing multi-modal representations. To address this limitation, we propose a novel Optimal Transport Adapter Tuning (OTAT) framework aimed at constructing an ideal Platonic representational space through optimal transport (OT) theory. This framework seeks to harmonize rich visual information with less dense textual cues, enabling effective cross-modal information transfer and complementarity. Central to this approach is the Optimal Transport Adapter (OTA), which employs a cross-modal attention mechanism to enrich textual representations and facilitate subsequent better information interaction. By transforming the network optimization into an OT optimization problem, OTA establishes efficient pathways for balanced information exchange between modalities. Moreover, we introduce a sample-level Entropy-Aware Weighted (EAW) loss, which combines difficulty-weighted similarity scores with entropy-based regularization. This loss function provides finer control over the OT optimization process, enhancing its solvability and stability. Our framework offers a scalable and efficient solution for advancing multimodal learning in remote sensing applications. Extensive experiments on benchmark datasets demonstrate that OTAT achieves state-of-the-art performance in FS-RSSC, significantly improving the model performance and generalization.

Zhong Ji, Weilong Cao, Yan Zhang et al.

Diffusion models has emerged as a powerful framework for tasks like image controllable generation and dense prediction. However, existing models often struggle to capture underlying semantics (e.g., edges, textures, shapes) and effectively utilize in-context learning, limiting their contextual understanding and image generation quality. Additionally, high computational costs and slow inference speeds hinder their real-time applicability. To address these challenges, we propose Underlying Semantic Diffusion (US-Diffusion), an enhanced diffusion model that boosts underlying semantics learning, computational efficiency, and in-context learning capabilities on multi-task scenarios. We introduce Separate & Gather Adapter (SGA), which decouples input conditions for different tasks while sharing the architecture, enabling better in-context learning and generalization across diverse visual domains. We also present a Feedback-Aided Learning (FAL) framework, which leverages feedback signals to guide the model in capturing semantic details and dynamically adapting to task-specific contextual cues. Furthermore, we propose a plug-and-play Efficient Sampling Strategy (ESS) for dense sampling at time steps with high-noise levels, which aims at optimizing training and inference efficiency while maintaining strong in-context learning performance. Experimental results demonstrate that US-Diffusion outperforms the state-of-the-art method, achieving an average reduction of 7.47 in FID on Map2Image tasks and an average reduction of 0.026 in RMSE on Image2Map tasks, while achieving approximately 9.45 times faster inference speed. Our method also demonstrates superior training efficiency and in-context learning capabilities, excelling in new datasets and tasks, highlighting its robustness and adaptability across diverse visual domains.

Jingren Liu, Zhong Ji, Yanwei Pang et al.

The proliferation of Few-Shot Class Incremental Learning (FSCIL) methodologies has highlighted the critical challenge of maintaining robust anti-amnesia capabilities in FSCIL learners. In this paper, we present a novel conceptualization of anti-amnesia in terms of mathematical generalization, leveraging the Neural Tangent Kernel (NTK) perspective. Our method focuses on two key aspects: ensuring optimal NTK convergence and minimizing NTK-related generalization loss, which serve as the theoretical foundation for cross-task generalization. To achieve global NTK convergence, we introduce a principled meta-learning mechanism that guides optimization within an expanded network architecture. Concurrently, to reduce the NTK-related generalization loss, we systematically optimize its constituent factors. Specifically, we initiate self-supervised pre-training on the base session to enhance NTK-related generalization potential. These self-supervised weights are then carefully refined through curricular alignment, followed by the application of dual NTK regularization tailored specifically for both convolutional and linear layers. Through the combined effects of these measures, our network acquires robust NTK properties, ensuring optimal convergence and stability of the NTK matrix and minimizing the NTK-related generalization loss, significantly enhancing its theoretical generalization. On popular FSCIL benchmark datasets, our NTK-FSCIL surpasses contemporary state-of-the-art approaches, elevating end-session accuracy by 2.9\% to 9.3\%.

Aqi Gao, Yanwei Pang, Jing Nie et al.

Fast stereo based 3D object detectors have made great progress recently. However, they lag far behind high-precision stereo based methods in accuracy. We argue that the main reason is due to the poor geometry-aware feature representation in 3D space. To solve this problem, we propose an efficient stereo geometry network (ESGN). The key in our ESGN is an efficient geometry-aware feature generation (EGFG) module. Our EGFG module first uses a stereo correlation and reprojection module to construct multi-scale stereo volumes in camera frustum space, second employs a multi-scale BEV projection and fusion module to generate multiple geometry-aware features. In these two steps, we adopt deep multi-scale information fusion for discriminative geometry-aware feature generation, without any complex aggregation networks. In addition, we introduce a deep geometry-aware feature distillation scheme to guide stereo feature learning with a LiDAR-based detector. The experiments are performed on the classical KITTI dataset. On KITTI test set, our ESGN outperforms the fast state-of-art-art detector YOLOStereo3D by 5.14\% on mAP$_{3d}$ at 62$ms$. To the best of our knowledge, our ESGN achieves a best trade-off between accuracy and speed. We hope that our efficient stereo geometry network can provide more possible directions for fast 3D object detection. Our source code will be released.

Xiyao Liu, Zhong Ji, Yanwei Pang et al.

The domain shift between the source and target domain is the main challenge in Cross-Domain Few-Shot Learning (CD-FSL). However, the target domain is absolutely unknown during the training on the source domain, which results in lacking directed guidance for target tasks. We observe that since there are similar backgrounds in target domains, it can apply self-labeled samples as prior tasks to transfer knowledge onto target tasks. To this end, we propose a task-expansion-decomposition framework for CD-FSL, called Self-Taught (ST) approach, which alleviates the problem of non-target guidance by constructing task-oriented metric spaces. Specifically, Weakly Supervised Object Localization (WSOL) and self-supervised technologies are employed to enrich task-oriented samples by exchanging and rotating the discriminative regions, which generates a more abundant task set. Then these tasks are decomposed into several tasks to finish the task of few-shot recognition and rotation classification. It helps to transfer the source knowledge onto the target tasks and focus on discriminative regions. We conduct extensive experiments under the cross-domain setting including 8 target domains: CUB, Cars, Places, Plantae, CropDieases, EuroSAT, ISIC, and ChestX. Experimental results demonstrate that the proposed ST approach is applicable to various metric-based models, and provides promising improvements in CD-FSL.

Zhong Ji, Zhishen Hou, Xiyao Liu et al.

Semantic information provides intra-class consistency and inter-class discriminability beyond visual concepts, which has been employed in Few-Shot Learning (FSL) to achieve further gains. However, semantic information is only available for labeled samples but absent for unlabeled samples, in which the embeddings are rectified unilaterally by guiding the few labeled samples with semantics. Therefore, it is inevitable to bring a cross-modal bias between semantic-guided samples and nonsemantic-guided samples, which results in an information asymmetry problem. To address this problem, we propose a Modal-Alternating Propagation Network (MAP-Net) to supplement the absent semantic information of unlabeled samples, which builds information symmetry among all samples in both visual and semantic modalities. Specifically, the MAP-Net transfers the neighbor information by the graph propagation to generate the pseudo-semantics for unlabeled samples guided by the completed visual relationships and rectify the feature embeddings. In addition, due to the large discrepancy between visual and semantic modalities, we design a Relation Guidance (RG) strategy to guide the visual relation vectors via semantics so that the propagated information is more beneficial. Extensive experimental results on three semantic-labeled datasets, i.e., Caltech-UCSD-Birds 200-2011, SUN Attribute Database, and Oxford 102 Flower, have demonstrated that our proposed method achieves promising performance and outperforms the state-of-the-art approaches, which indicates the necessity of information symmetry.

Aqi Gao, Jiale Cao, Yanwei Pang

Pseudo-LiDAR based 3D object detectors have gained popularity due to their high accuracy. However, these methods need dense depth supervision and suffer from inferior speed. To solve these two issues, a recently introduced RTS3D builds an efficient 4D Feature-Consistency Embedding (FCE) space for the intermediate representation of object without depth supervision. FCE space splits the entire object region into 3D uniform grid latent space for feature sampling point generation, which ignores the importance of different object regions. However, we argue that, compared with the inner region, the outer region plays a more important role for accurate 3D detection. To encode more information from the outer region, we propose a shape prior non-uniform sampling strategy that performs dense sampling in outer region and sparse sampling in inner region. As a result, more points are sampled from the outer region and more useful features are extracted for 3D detection. Further, to enhance the feature discrimination of each sampling point, we propose a high-level semantic enhanced FCE module to exploit more contextual information and suppress noise better. Experiments on the KITTI dataset are performed to show the effectiveness of the proposed method. Compared with the baseline RTS3D, our proposed method has 2.57% improvement on AP3d almost without extra network parameters. Moreover, our proposed method outperforms the state-of-the-art methods without extra supervision at a real-time speed.

Wenguan Wang, Hailong Zhu, Jifeng Dai et al.

Human parsing is for pixel-wise human semantic understanding. As human bodies are underlying hierarchically structured, how to model human structures is the central theme in this task. Focusing on this, we seek to simultaneously exploit the representational capacity of deep graph networks and the hierarchical human structures. In particular, we provide following two contributions. First, three kinds of part relations, i.e., decomposition, composition, and dependency, are, for the first time, completely and precisely described by three distinct relation networks. This is in stark contrast to previous parsers, which only focus on a portion of the relations and adopt a type-agnostic relation modeling strategy. More expressive relation information can be captured by explicitly imposing the parameters in the relation networks to satisfy the specific characteristics of different relations. Second, previous parsers largely ignore the need for an approximation algorithm over the loopy human hierarchy, while we instead address an iterative reasoning process, by assimilating generic message-passing networks with their edge-typed, convolutional counterparts. With these efforts, our parser lays the foundation for more sophisticated and flexible human relation patterns of reasoning. Comprehensive experiments on five datasets demonstrate that our parser sets a new state-of-the-art on each.

Jin Xie, Yanwei Pang, Hisham Cholakkal et al.

Detecting pedestrians, especially under heavy occlusions, is a challenging computer vision problem with numerous real-world applications. This paper introduces a novel approach, termed as PSC-Net, for occluded pedestrian detection. The proposed PSC-Net contains a dedicated module that is designed to explicitly capture both inter and intra-part co-occurrence information of different pedestrian body parts through a Graph Convolutional Network (GCN). Both inter and intra-part co-occurrence information contribute towards improving the feature representation for handling varying level of occlusions, ranging from partial to severe occlusions. Our PSC-Net exploits the topological structure of pedestrian and does not require part-based annotations or additional visible bounding-box (VBB) information to learn part spatial co-occurrence. Comprehensive experiments are performed on two challenging datasets: CityPersons and Caltech datasets. The proposed PSC-Net achieves state-of-the-art detection performance on both. On the heavy occluded (\textbf{HO}) set of CityPerosns test set, our PSC-Net obtains an absolute gain of 4.0\% in terms of log-average miss rate over the state-of-the-art with same backbone, input scale and without using additional VBB supervision. Further, PSC-Net improves the state-of-the-art from 37.9 to 34.8 in terms of log-average miss rate on Caltech (\textbf{HO}) test set.

Wenguan Wang, Zhijie Zhang, Siyuan Qi et al.

This work proposes to combine neural networks with the compositional hierarchy of human bodies for efficient and complete human parsing. We formulate the approach as a neural information fusion framework. Our model assembles the information from three inference processes over the hierarchy: direct inference (directly predicting each part of a human body using image information), bottom-up inference (assembling knowledge from constituent parts), and top-down inference (leveraging context from parent nodes). The bottom-up and top-down inferences explicitly model the compositional and decompositional relations in human bodies, respectively. In addition, the fusion of multi-source information is conditioned on the inputs, i.e., by estimating and considering the confidence of the sources. The whole model is end-to-end differentiable, explicitly modeling information flows and structures. Our approach is extensively evaluated on four popular datasets, outperforming the state-of-the-arts in all cases, with a fast processing speed of 23fps. Our code and results have been released to help ease future research in this direction.

Yazhao Li, Yanwei Pang, Jianbing Shen et al.

Due to the advantages of real-time detection and improved performance, single-shot detectors have gained great attention recently. To solve the complex scale variations, single-shot detectors make scale-aware predictions based on multiple pyramid layers. However, the features in the pyramid are not scale-aware enough, which limits the detection performance. Two common problems in single-shot detectors caused by object scale variations can be observed: (1) small objects are easily missed; (2) the salient part of a large object is sometimes detected as an object. With this observation, we propose a new Neighbor Erasing and Transferring (NET) mechanism to reconfigure the pyramid features and explore scale-aware features. In NET, a Neighbor Erasing Module (NEM) is designed to erase the salient features of large objects and emphasize the features of small objects in shallow layers. A Neighbor Transferring Module (NTM) is introduced to transfer the erased features and highlight large objects in deep layers. With this mechanism, a single-shot network called NETNet is constructed for scale-aware object detection. In addition, we propose to aggregate nearest neighboring pyramid features to enhance our NET. NETNet achieves 38.5% AP at a speed of 27 FPS and 32.0% AP at a speed of 55 FPS on MS COCO dataset. As a result, NETNet achieves a better trade-off for real-time and accurate object detection.

Tiancai Wang, Rao Muhammad Anwer, Muhammad Haris Khan et al.

Human-object interaction detection is an important and relatively new class of visual relationship detection tasks, essential for deeper scene understanding. Most existing approaches decompose the problem into object localization and interaction recognition. Despite showing progress, these approaches only rely on the appearances of humans and objects and overlook the available context information, crucial for capturing subtle interactions between them. We propose a contextual attention framework for human-object interaction detection. Our approach leverages context by learning contextually-aware appearance features for human and object instances. The proposed attention module then adaptively selects relevant instance-centric context information to highlight image regions likely to contain human-object interactions. Experiments are performed on three benchmarks: V-COCO, HICO-DET and HCVRD. Our approach outperforms the state-of-the-art on all datasets. On the V-COCO dataset, our method achieves a relative gain of 4.4% in terms of role mean average precision ($mAP_{role}$), compared to the existing best approach.

Zhong Ji, Xuejie Yu, Yunlong Yu et al.

Zero-Shot Classification (ZSC) equips the learned model with the ability to recognize the visual instances from the novel classes via constructing the interactions between the visual and the semantic modalities. In contrast to the traditional image classification, ZSC is easily suffered from the class-imbalance issue since it is more concerned with the class-level knowledge transfer capability. In the real world, the class samples follow a long-tailed distribution, and the discriminative information in the sample-scarce seen classes is hard to be transferred to the related unseen classes in the traditional batch-based training manner, which degrades the overall generalization ability a lot. Towards alleviating the class imbalance issue in ZSC, we propose a sample-balanced training process to encourage all training classes to contribute equally to the learned model. Specifically, we randomly select the same number of images from each class across all training classes to form a training batch to ensure that the sample-scarce classes contribute equally as those classes with sufficient samples during each iteration. Considering that the instances from the same class differ in class representativeness, we further develop an efficient semantics-guided feature fusion model to obtain discriminative class visual prototype for the following visual-semantic interaction process via distributing different weights to the selected samples based on their class representativeness. Extensive experiments on three imbalanced ZSC benchmark datasets for both the Traditional ZSC (TZSC) and the Generalized ZSC (GZSC) tasks demonstrate our approach achieves promising results especially for the unseen categories those are closely related to the sample-scarce seen categories.

Zhong Ji, Haoran Wang, Jungong Han et al.

This paper studies the task of matching image and sentence, where learning appropriate representations across the multi-modal data appears to be the main challenge. Unlike previous approaches that predominantly deploy symmetrical architecture to represent both modalities, we propose Saliency-guided Attention Network (SAN) that asymmetrically employs visual and textual attention modules to learn the fine-grained correlation intertwined between vision and language. The proposed SAN mainly includes three components: saliency detector, Saliency-weighted Visual Attention (SVA) module, and Saliency-guided Textual Attention (STA) module. Concretely, the saliency detector provides the visual saliency information as the guidance for the two attention modules. SVA is designed to leverage the advantage of the saliency information to improve discrimination of visual representations. By fusing the visual information from SVA and textual information as a multi-modal guidance, STA learns discriminative textual representations that are highly sensitive to visual clues. Extensive experiments demonstrate SAN can substantially improve the state-of-the-art results on the benchmark Flickr30K and MSCOCO datasets by a large margin.

Yunlong Yu, Zhong Ji, Yanwei Pang et al.

Existing generative Zero-Shot Learning (ZSL) methods only consider the unidirectional alignment from the class semantics to the visual features while ignoring the alignment from the visual features to the class semantics, which fails to construct the visual-semantic interactions well. In this paper, we propose to synthesize visual features based on an auto-encoder framework paired with bi-adversarial networks respectively for visual and semantic modalities to reinforce the visual-semantic interactions with a bi-directional alignment, which ensures the synthesized visual features to fit the real visual distribution and to be highly related to the semantics. The encoder aims at synthesizing real-like visual features while the decoder forces both the real and the synthesized visual features to be more related to the class semantics. To further capture the discriminative information of the synthesized visual features, both the real and synthesized visual features are forced to be classified into the correct classes via a classification network. Experimental results on four benchmark datasets show that the proposed approach is particularly competitive on both the traditional ZSL and the generalized ZSL tasks.